© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 553
    Prev
    Next
    INDEX
    Explanations

    programs and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acompañ
    -1.12
    我了
    -1.10
     hope
    -1.06
    孩
    -1.06
     necessário
    -1.05
     fabulous
    -1.02
     problematic
    -1.02
    佇
    -1.00
     marvelous
    -1.00
     mohou
    -1.00
    POSITIVE LOGITS
    program
    1.83
     program
    1.59
    matically
    1.56
    Program
    1.52
    rogram
    1.42
     ریزی
    1.42
     PROGRAM
    1.39
     передач
    1.30
    プログラム
    1.30
     программа
    1.28
    Activations Density 0.032%

    No Known Activations